diff options
| author | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-18 15:13:41 -0500 |
|---|---|---|
| committer | Leonard Richardson <leonard.richardson@canonical.com> | 2011-02-18 15:13:41 -0500 |
| commit | 8249b803d9bab9c06be02a244e629cb732f4f5b1 (patch) | |
| tree | 447cddabac142fefd583df1acd6268f6abcb8f5c /tests/test_html5lib.py | |
| parent | 0dda99b15112df7225e647db9702fbd62dcc8ea8 (diff) | |
| parent | e170ff33e67e806cf33e2e51fcefcfa0b9310d96 (diff) | |
Ported the rest of the HTML tests, including tests of broken HTML from the TODO. Made Unicode, Dammit PEP-8 compliant.
Diffstat (limited to 'tests/test_html5lib.py')
| -rw-r--r-- | tests/test_html5lib.py | 56 |
1 files changed, 49 insertions, 7 deletions
diff --git a/tests/test_html5lib.py b/tests/test_html5lib.py index 59d84a3..3045b02 100644 --- a/tests/test_html5lib.py +++ b/tests/test_html5lib.py @@ -131,14 +131,56 @@ class TestHTML5BuilderInvalidMarkup(TestLXMLBuilderInvalidMarkup): self.assertEquals(comment, 'b <p') self.assertEquals(str2, 'c') - def test_foo(self): - isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>""" - soup = self.soup(isolatin) + def test_document_starts_with_bogus_declaration(self): + soup = self.soup('<! Foo >a') + # 'Foo' becomes a comment that appears before the HTML. + comment = soup.contents[0] + self.assertTrue(isinstance(comment, Comment)) + self.assertEquals(comment, 'Foo') - utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode()) - utf8 = utf8.replace("\xe9", "\xc3\xa9") + self.assertEquals(self.find(text="a") == "a") - #print soup + def test_attribute_value_was_closed_by_subsequent_tag(self): + markup = """<a href="foo</a>, </a><a href="bar">baz</a>""" + soup = self.soup(markup) + # The string between the first and second quotes was interpreted + # as the value of the 'href' attribute. + self.assertEquals(soup.a['href'], 'foo</a>, </a><a href=') + + #The string after the second quote (bar"), was treated as an + #empty attribute called bar". + self.assertEquals(soup.a['bar"'], '') + self.assertEquals(soup.a.string, "baz") + + def test_document_starts_with_bogus_declaration(self): + soup = self.soup('<! Foo ><p>a</p>') + # The declaration becomes a comment. + comment = soup.contents[0] + self.assertTrue(isinstance(comment, Comment)) + self.assertEquals(comment, ' Foo ') + self.assertEquals(soup.p.string, 'a') + + def test_document_ends_with_incomplete_declaration(self): + soup = self.soup('<p>a<!b') + # This becomes a string 'a'. The incomplete declaration is ignored. + # Compare html5lib, which turns it into a comment. + s, comment = soup.p.contents + self.assertEquals(s, 'a') + self.assertTrue(isinstance(comment, Comment)) + self.assertEquals(comment, 'b') + + def test_entity_was_not_finished(self): + soup = self.soup("<p><Hello>") + # Compare html5lib, which completes the entity. + self.assertEquals(soup.p.string, "<Hello>") + + def test_nonexistent_entity(self): + soup = self.soup("<p>foo&#bar;baz</p>") + self.assertEquals(soup.p.string, "foo&#bar;baz") + + # Compare a real entity. + soup = self.soup("<p>foodbaz</p>") + self.assertEquals(soup.p.string, "foodbaz") class TestHTML5LibEncodingConversion(TestLXMLBuilderEncodingConversion): @@ -151,7 +193,7 @@ class TestHTML5LibEncodingConversion(TestLXMLBuilderEncodingConversion): # Hebrew encoding) to UTF-8. soup = self.soup(self.HEBREW_DOCUMENT, fromEncoding="iso-8859-8") - self.assertEquals(soup.originalEncoding, 'iso8859-8') + self.assertEquals(soup.original_encoding, 'iso8859-8') self.assertEquals( soup.encode('utf-8'), self.HEBREW_DOCUMENT.decode("iso-8859-8").encode("utf-8")) |